Loading…
Fuzzy neural network theory and application /
This book systematically synthesizes research achievements in the field of fuzzy neural networks in recent years. It also provides a comprehensive presentation of the developments in fuzzy neural networks, with regard to theory as well as their application to system modeling and image restoration. S...
| Call Number: | Libro Electrónico |
|---|---|
| Main Author: | |
| Other Authors: | |
| Format: | Electronic eBook |
| Language: | Inglés |
| Published: |
River Edge, NJ :
World Scientific,
2004.
|
| Series: | Series in machine perception and artificial intelligence ;
v. 59. |
| Subjects: | |
| Online Access: | Texto completo |
Table of Contents:
- Foreword; Preface; Chapter I Introduction; S1.1 Classification of fuzzy neural networks; S1.2 Fuzzy neural networks with fuzzy operators; S1.3 Puzzified neural networks; 1.3.1 Learning algorithm for regular FNN's; 1.3.2 Universal approximation of regular FNN's; S1.4 Fuzzy systems and fuzzy inference networks; 1.4.1 Fuzzy systems; 1.4.2 Fuzzy inference networks; S1.5 Fuzzy techniques in image restoration; 1.5.1 Crisp nonlinear filters; 1.5.2 Fuzzy filters; S1.6 Notations and preliminaries; S1.7 Outline of the topics of the chapters; References.
- Chapter II Fuzzy Neural Networks for Storing and ClassifyingS2.1 Two layer max-min fuzzy associative memory; 2.1.1 FAM with threshold; 2.1.2 Simulation example; S2.2 Fuzzy 6-learning algorithm; 2.2.1 FAM's based on 'V
- /\'; 2.2.2 FAM's based on 'V
- *'; S2.3 BP learning algorithm of FAM's; 2.3.1 Two analytic functions; 2.3.2 BP learning algorithm; S2.4 Fuzzy ART and fuzzy ARTMAP; 2.4.1 ART1 architecture; 2.4.2 Fuzzy ART; 2.4.3 Fuzzy ARTMAP; 2.4.4 Real examples; References; Chapter III Fuzzy Associative Memory-Feedback Networks; S3.1 Fuzzy Hopfield networks.
- 3.1.1 Attractor and attractive basin3.1.2 Learning algorithm based on fault-tolerance; 3.1.3 Simulation example; S3.2 Fuzzy Hopfield network with threshold; 3.2.1 Attractor and stability; 3.2.2 Analysis of fault-tolerance; S3.3 Stability and fault-tolerance of FBAM; 3.3.1 Stability analysis; 3.3.2 Fault-tolerance analysis; 3.3.3 A simulation example; S3.4 Learning algorithm for FBAM; 3.4.1 Learning algorithm based on fault-tolerance; 3.4.2 A simulation example; 3.4.3 Optimal fault-tolerance; 3.4.4 An example; S3.5 Connection network of FBAM; 3.5.1 Fuzzy row-restricted matrix.
- 3.5.2 The connection relations of attractors3.5.3 The elementary memory of (R L); 3.5.4 The transition laws of states; S3.6 Equilibrium analysis of fuzzy Hopfield network; 3.6.1 Connection relations of attractors; 3.6.2 Elementary memory of W; 3.6.3 The state transition laws; References; Chapter IV Regular Fuzzy Neural Networks; S4.1 Regular fuzzy neuron and regular FNN; 4.1.1 Regular fuzzy neuron; 4.1.2 Regular fuzzy neural network; 4.1.3 A counter example of universal approximation; 4.1.4 An example of universal approximation; S4.2 Learning algorithms; 4.2.1 Preliminaries.
- 4.2.2 Calculus of V
- /\ functions4.2.3 Error function; 4.2.4 Partial derivatives of error function; 4.2.5 Learning algorithm and simulation; S4.3 Conjugate gradient algorithm for fuzzy weights; 4.3.1 Fuzzy CG algorithm and convergence; 4.3.2 GA for finding optimal learning constant; 4.3.3 Simulation examples; S4.4 Universal approximation to fuzzy valued functions; 4.4.1 Fuzzy valued Bernstein polynomial; 4.4.2 Four-layer regular feedforward FNN; 4.4.3 An example; S4.5 Approximation analysis of regular FNN; 4.5.1 Closure fuzzy mapping; 4.5.2 Learning algorithm.